Detailed Analysis and Evaluation of Keypoint Extraction Methods

摘要：

In this paper, some existing keypoint extraction algorithms, including Harris, SIFT, SURF and CenSurE, are analyzed and evaluated based on images containing view, scale and rotation changes. After these algorithms are introduced, analysis on Harris and SIFT detectors has been carried out, which can lead to better understanding about their performances. Comparative experiments have been conducted to investigate repeatability, matching ratio, accuracy, characteristic distribution and computational efficiency. At last, the advantage and disadvantage of each method are summarized and the future works to improve their performances is also suggested.

关键词： keypoint extraction harris SIFT SURF censure

作者: Xianliang Wu Zongying Shi Yisheng Zhong

作者单位: Tsinghua National Laboratory for Information Science and Technology Department of Automation Tsinghua University Beijing, China

会议类型: 国际会议

会议名称: The 2010 International Conference on Computer Application and System Modeling(2010计算机应用与系统建模国际会议 ICCASM 2010)

会议地点: 太原

会议语种:英文

页码: 562-566

在线出版日期: 2010-10-22（万方平台首次上网日期，不代表论文的发表时间）